TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems

Doan, Bao Gia; Xue, Minhui; Ma, Shiqing; Abbasnejad, Ehsan; Ranasinghe, Damith C.

doi:10.1109/tifs.2022.3198857

Cited by 35 publications

(18 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Bao [38] et al pointed out the existing physical adversarial patches are visually conspicuous. To address the issue, the author proposed to use a generator to construct naturalistic adversarial patches.…”

Section: Tntattackmentioning

confidence: 99%

“…Moreover, with the increasingly maturing of DNNs in commercial deployment, exploring the physical attack is more urgent for enhancing the robustness of DNN-based systems. Although some works have reviewed the development of physical attacks [22,28], they are out-of-date since plenty of novel physical attacks have emerged [29][30][31][32][33][34][35][36][37][38][39] in the past two years. Concurrent to our survey, although [40,41] review physical attacks, they only review some of the physical attacks, i.e., 43 and 46 publications, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Physical Adversarial Attack in Computer Vision

Wang¹,

Wen²,

Jiang³

et al. 2023

Preprint

View full text Add to dashboard Cite

In the past decade, deep learning has dramatically changed the traditional hand-craft feature manner with strong feature learning capability, promoting the tremendous improvement of conventional tasks. However, deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples crafted by small noise, which is imperceptible to human observers but can make DNNs misbehave. Existing adversarial attacks can be divided into digital and physical adversarial attacks. The former is designed to pursue strong attack performance in lab environments while hardly remaining effective when applied to the physical world. In contrast, the latter focus on developing physical deployable attacks, which are more robust in complex physical environmental conditions (e.g., brightness, occlusion, etc.). Recently, with the increasing deployment of the DNN-based system in the real world, enhancing the robustness of these systems is an emergency, while exploring physical adversarial attacks exhaustly is the precondition. To this end, this paper reviews the development of physical adversarial attacks against DNN-based computer vision tasks (i.e., image recognition and object detection tasks), which can provide beneficial information for developing stronger physical adversarial attacks. For completeness, we also briefly introduce the works that do not involve physical attacks but are closely related to them. Specifically, we first proposed a taxonomy to summarize the current physical adversarial attacks. Then we briefly discuss the existing physical attacks and focus on the technique for improving the robustness of physical attacks under complex physical environmental conditions. Finally, we discuss the issues of the current physical adversarial attacks to be solved and give promising directions.

show abstract

Section: Tntattackmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Survey on Physical Adversarial Attack in Computer Vision

Wang¹,

Wen²,

Jiang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Duan et al [91] demonstrates that DNNs can be easily deceived using only a laser beam. Research [166] uncovers the presence of an intriguing category of spatially constrained, physically feasible adversarial examples, i.e., Universal NaTuralistic adversarial paTches (TnTs). TnTs are crafted by examining the full range of spatially bounded adversarial examples and the natural input space within generative adversarial networks (GANs).…”

Section: Black-box Attacksmentioning

confidence: 99%

Benchmarking Adversarial Patch Against Aerial Detection

Lian

Mei

Zhang

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulnerable to different types of noises, particularly adversarial noises. Surprisingly, there has been a lack of comprehensive studies on the robustness of RS tasks, prompting us to undertake a thorough survey and benchmark on the robustness of image classification and object detection in RS. To our best knowledge, this study represents the first comprehensive examination of both natural robustness and adversarial robustness in RS tasks. Specifically, we have curated and made publicly available datasets that contain natural and adversarial noises. These datasets serve as valuable resources for evaluating the robustness of DNNs-based models. To provide a comprehensive assessment of model robustness, we conducted meticulous experiments with numerous different classifiers and detectors, encompassing a wide range of mainstream methods. Through rigorous evaluation, we have uncovered insightful and intriguing findings, which shed light on the relationship between adversarial noise crafting and model training, yielding a deeper understanding of the susceptibility and limitations of various models, and providing guidance for the development of more resilient and robust models

show abstract

“…Recently, Bao [92] et al pointed out the existing physical adversarial patches are visually non-naturalistic. To address such issues, the author proposed to exploit a generator to construct naturalistic adversarial patches.…”

Section: B General Image Recognitionmentioning

confidence: 99%